You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is challenging to get reliable but it would be great to implement some of the "demo" algorithms into the code base.
There has already been work that detects number of leaves, plant width, etc.
There needs to be some pre-processing filters to determine if an image is valid to be processed. The main concern is to detect occlusion (what happens when the plants get big and they overlap?) Can we put the plant site locations in the device config file? Then make sure the image has isolated clusters around each plant site. Then if there is not occlusion, run through the leaf count processor. The leaf count processor will likely need to know the cultivar classification (Basil leaves vs. Arugula leaves).
The text was updated successfully, but these errors were encountered:
jakerye
changed the title
integrate image processing algorithms to detect low hanging fruit
integrate image processing algorithms to detect foliage area
Oct 31, 2018
Maybe you could tag the plant sites with some kind of unique fiducial marker like a 2D barcode. That might also help with identifying cameras for issue #168 (multiple cameras). Eventually the markers would get occluded, but you could identify the sites at transplant time. You could even take it so far as to have stickers or snap in labels to uniquely identify each seedling (traceable back to cultivar classification, seed provenance, etc.)
This is challenging to get reliable but it would be great to implement some of the "demo" algorithms into the code base.
There has already been work that detects number of leaves, plant width, etc.
There needs to be some pre-processing filters to determine if an image is valid to be processed. The main concern is to detect occlusion (what happens when the plants get big and they overlap?) Can we put the plant site locations in the device config file? Then make sure the image has isolated clusters around each plant site. Then if there is not occlusion, run through the leaf count processor. The leaf count processor will likely need to know the cultivar classification (Basil leaves vs. Arugula leaves).
The text was updated successfully, but these errors were encountered: